Image-Conditioned Graph Generation for Road Network Extraction

Abstract

Deep generative models for graphs have shown great promise in the area of drug design, but have so far found little application beyond generating graph-structured molecules. In this work, we demonstrate a proof of concept for the challenging task of road network extraction from image data. This task can be framed as image-conditioned graph generation, for which we develop the Generative Graph Transformer (GGT), a deep autoregressive model that makes use of attention mechanisms for image conditioning and the recurrent generation of graphs. We benchmark GGT on the application of road network extraction from semantic segmentation data. For this, we introduce the Toulouse Road Network dataset, based on real-world publicly-available data. We further propose the StreetMover distance: a metric based on the Sinkhorn distance for effectively evaluating the quality of road network generation. The code and dataset are publicly available.

Presented at NeurIPS 2019 Workshop on Graph Representation Learning

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• MolGAN: An implicit generative model for small molecular graphs
• Learning Deep Generative Models of Graphs
• SpaceNet: A Remote Sensing Dataset and Challenge Series
• One Model To Learn Them All
• Road Segmentation in SAR Satellite Images with Deep Fully-Convolutional Neural Networks
• Efficient Graph Generation with Graph Recurrent Attention Networks
• Neural Turtle Graphics for Modeling City Road Layouts
• Neural Particle Smoothing for Sampling from Conditional Sequence Models

Cited by in corpus (7)

• RNGDet: Road Network Graph Detection by Transformer in Aerial Images
• iCurb: Imitation Learning-based Detection of Road Curbs using Aerial Images for Autonomous Driving
• clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation
• Topo-boundary: A Benchmark Dataset on Topological Road-boundary Detection Using Aerial Images for Autonomous Driving
• Deep Generative Modeling in Network Science with Applications to Public Policy Research
• Self-Labeling of Fully Mediating Representations by Graph Alignment
• Knowledge Generation -- Variational Bayes on Knowledge Graphs